[vLLM IR] 1/N Implement IR skeleton and rms_norm op (#33825)
Signed-off-by: Luka Govedič <lgovedic@redhat.com> Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com> Signed-off-by: chzhang <chaojun.zhang@intel.com> Signed-off-by: Luka Govedic <luka.govedic@gmail.com> Co-authored-by: Xinyu Chen <xinyu1.chen@intel.com> Co-authored-by: Chaojun Zhang <chaojun.zhang@intel.com> Co-authored-by: Luka Govedič <ProExpertProg@h100-01.nemg-001.lab.rdu2.dc.redhat.com>
This commit is contained in:
co-authored by
Xinyu Chen
Chaojun Zhang
Luka Govedič
parent
0fab52f0aa
commit
40bb175027
@@ -17,6 +17,7 @@ if TYPE_CHECKING:
|
||||
from torch.distributed import PrefixStore, ProcessGroup
|
||||
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.config.kernel import IrOpPriorityConfig
|
||||
from vllm.inputs import EngineInput
|
||||
from vllm.pooling_params import PoolingParams
|
||||
from vllm.sampling_params import SamplingParams
|
||||
@@ -931,6 +932,16 @@ class Platform:
|
||||
"num_compute_units is not implemented for the current platform."
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def get_default_ir_op_priority(
|
||||
cls, vllm_config: "VllmConfig"
|
||||
) -> "IrOpPriorityConfig":
|
||||
"""Get the default IR op priority for the current platform."""
|
||||
from vllm.config.kernel import IrOpPriorityConfig
|
||||
|
||||
# Native always used by default. Platforms can override this behavior.
|
||||
return IrOpPriorityConfig.with_default(["native"])
|
||||
|
||||
|
||||
class UnspecifiedPlatform(Platform):
|
||||
_enum = PlatformEnum.UNSPECIFIED
|
||||
|
||||
Reference in New Issue
Block a user